Associating Clinical Decision Support Use with Clinical Outcomes in a Visual Analytics Display

将临床决策支持的使用与可视化分析显示中的临床结果相关联

• 批准号: 9907877
• 负责人: Evan William Orenstein
• 金额: $ 22.5万
• 依托单位: PHRASE HEALTH, INC.
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-16 至 2020-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9907877
• 关键词: Adherence; Adoption; Advocate; Antibiotics; Architecture; Bundling; Caring; Child health care; Childhood; Clinical; Clinical effectiveness; Computer software; Data; Diagnosis; Diagnostic; Effectiveness; Electronic Health Record; Elements; Evaluation; Evidence based practice; Goals; Guideline Adherence; Guidelines; Health; Healthcare; Hospitals; Imagery; Individual; Inpatients; Institution; Intervention; Interview; Intuition; Knowledge; Knowledge Discovery; Length of Stay; Link; Manuals; Measures; Medical; Medical Research; Methods; Migraine; Modeling; Monitor; Outcome; Outcome Measure; Patient Care; Patient-Focused Outcomes; Patients; Pattern; Pediatric Hospitals; Pharmaceutical Preparations; Phase; Philadelphia; Population; Process; Process Measure; Quality of Care; Resources; Sepsis; Source; Surveys; Testing; Therapeutic; Variant; Visual; base; clinical care; clinical decision support; cohort; contextual factors; dashboard; data modeling; database schema; health care delivery; health care service organization; improved; inpatient service; insight; interest; mortality; novel; phrases; programs; readmission rates; support tools; tool; usability; user centered design

Project Summary/Abstract Clinical decision support (CDS) is a process for enhancing health-related decisions and actions with pertinent, organized clinical knowledge and patient information to improve healthcare delivery. For example, doctors may have trouble remembering to order all guideline-recommended care for sepsis. CDS delivered via an order set in the electronic health record (EHR) can simplify this process and reduce mortality by bundling the recommended diagnostic and therapeutic orders together. More generally, CDS has the potential to improve patient outcomes by facilitating adherence to evidence-based practices (EBPs). However, it may fail to reach this potential because: (1) the CDS tool is underutilized; (2) the user may not follow the recommended action from the CDS; (3) the recommended action may not lead to the EBP; and/or (4) the EBP may not translate to the expected outcome in a novel population. Healthcare organizations need an efficient, rigorous, and scalable process evaluation method to diagnose when and why CDS is not leading to the intended improvements. Our long-term objective is to empower organizations to efficiently incorporate scientific knowledge into high value clinical care through incremental, data-driven improvements of CDS informed by understanding of the relationships between CDS use, process measures, and patient outcomes. In Aim 1 of this proposal, we will establish the technical feasibility of associating CDS use patterns with process and outcome metrics using EHR-log data through a proof of concept demonstration focused on inpatient treatment of pediatric migraine. Both Children’s Healthcare of Atlanta (CHOA) and Children’s Hospital of Philadelphia (CHOP) have well defined patient cohorts, local clinical guidelines, order sets, and outcome metrics for the care of inpatient pediatric migraine patients. Phrase Health® has already developed a commercial CDS analytics product used by 3 institutions that organizes EHR-log data into an intuitive display that provides insight into how all an organization’s alerts and order sets are used. We will leverage these strengths to create a standard database schema for patient cohorts that links to Phrase Health©’s existing data model for order set use patterns. We will then verify the accuracy of this association through manual chart review. While we use inpatient migraine as a model, the architecture will generalize across clinical use cases. In Aim 2, we will use user-centered design best practices to develop a visual analytics dashboard for rapid identification of CDS improvement targets. We will then evaluate the effectiveness of the dashboard through scenario-based summative testing, in which we measure how accurately users identify CDS improvement targets with a functional dashboard based on real CDS data extracted in Aim 1. At the end of this project, we will have created and validated a novel, scalable CDS process evaluation tool with demonstrated technical feasibility at two institutions. This will advance healthcare organizations’ ability to improve patient outcomes through CDS and prepare us for a Phase 2 application focused on implementation.

项目总结/摘要 临床决策支持（CDS）是一个增强健康相关决策和行动的过程， 组织临床知识和患者信息，以改善医疗服务。例如，医生可能 很难记住所有指南推荐的脓毒症护理。通过订单集交付CDS 电子健康记录（EHR）中的可以通过捆绑 推荐的诊断和治疗顺序。更普遍地说，CDS有潜力改善 通过促进遵守循证实践（EBP）来改善患者结局。然而，它可能无法达到 这种可能性是因为：（1）CDS工具未得到充分利用;（2）用户可能没有遵循建议的操作 （3）建议的措施可能不会导致EBP;和/或（4）EBP可能不会转化为 在新人群中的预期结果。医疗保健组织需要一个高效、严格和可扩展的 过程评估方法，用于诊断CDS何时以及为何未实现预期改进。我们 长期目标是使组织能够有效地将科学知识转化为高价值 通过对CDS的增量、数据驱动的改进， CDS使用、过程测量和患者结局之间的关系。 在本提案的目标1中，我们将建立将CDS使用模式与 使用EHR日志数据的流程和结果指标，通过概念验证演示，重点是 儿科偏头痛的住院治疗。亚特兰大儿童保健（CHOA）和儿童医院 费城（CHOP）有明确的患者队列、当地临床指南、顺序集和结局 儿科偏头痛住院患者的护理指标。Phrase Health®已经开发出一种 3家机构使用的商业CDS分析产品，将EHR日志数据组织成直观的显示 它提供了对如何使用组织的所有警报和订单集的深入了解。我们将利用这些 为患者队列创建标准数据库模式，链接到Phrase Health©的现有数据 订单集使用模式的模型。然后，我们将通过手动图表验证此关联的准确性 审查.虽然我们使用住院偏头痛作为模型，但该架构将在临床用例中推广。 在目标2中，我们将使用以用户为中心的设计最佳实践来开发一个可视化的分析仪表板， 确定CDS改进目标。然后，我们将通过以下方式评估仪表板的有效性： 基于ESPRIO的总结性测试，我们在其中测量用户识别CDS改进的准确性 目标1中提取的真实的CDS数据为基础的功能仪表板。 在这个项目结束时，我们将创建并验证一个新颖的，可扩展的CDS过程评估工具 在两个机构证明了技术可行性。这将提高医疗保健组织的能力， 通过CDS改善患者治疗效果，并为专注于实施的第2阶段应用做好准备。